© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 56083
    Prev
    Next
    INDEX
    Explanations

    alphabet letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Richt
    -0.11
     numeral
    -0.09
    nage
    -0.09
    ä»ģ
    -0.09
    yor
    -0.08
    é½
    -0.08
    errno
    -0.08
    Ln
    -0.08
     Greenwich
    -0.08
    atif
    -0.08
    POSITIVE LOGITS
     letters
    0.43
     letter
    0.41
     Letter
    0.36
     Letters
    0.35
    letters
    0.32
     LETTER
    0.31
    letter
    0.31
    Letters
    0.30
    Letter
    0.30
    -letter
    0.26
    Activations Density 0.148%

    No Known Activations